{"total":50,"rows":[{"id":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355,"area":"ssm"},{"id":"2406.07522","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","created":"2024-06-11","cited_by_count":174,"area":"ssm"},{"id":"2408.15237","title":"The Mamba in the Llama: Distilling and Accelerating Hybrid Models","created":"2024-08-27","cited_by_count":122,"area":"ssm"},{"id":"2402.04248","title":"Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks","created":"2024-02-06","cited_by_count":105,"area":"ssm"},{"id":"2411.12537","title":"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues","created":"2024-11-19","cited_by_count":101,"area":"ssm"},{"id":"2402.19047","title":"Theoretical Foundations of Deep Selective State-Space Models","created":"2024-02-29","cited_by_count":74,"area":"ssm"},{"id":"2408.10189","title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models","created":"2024-08-19","cited_by_count":67,"area":"ssm"},{"id":"2401.13660","title":"MambaByte: Token-free Selective State Space Model","created":"2024-01-24","cited_by_count":59,"area":"ssm"},{"id":"2407.14207","title":"Longhorn: State Space Models are Amortized Online Learners","created":"2024-07-19","cited_by_count":59,"area":"ssm"},{"id":"2406.14528","title":"DeciMamba: Exploring the Length Extrapolation Potential of Mamba","created":"2024-06-20","cited_by_count":49,"area":"ssm"},{"id":"2402.03170","title":"Is Mamba Capable of In-Context Learning?","created":"2024-02-05","cited_by_count":45,"area":"ssm"},{"id":"2407.09941","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","created":"2024-07-13","cited_by_count":44,"area":"ssm"},{"id":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40,"area":"ssm"},{"id":"2407.18232","title":"LION: Linear Group RNN for 3D Object Detection in Point Clouds","created":"2024-07-25","cited_by_count":38,"area":"ssm"},{"id":"2605.22791","title":"Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention","created":"2026-05-21","cited_by_count":33,"area":"ssm"},{"id":"2406.19369","title":"Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model","created":"2024-06-27","cited_by_count":18,"area":"ssm"},{"id":"2501.00658","title":"Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing","created":"2024-12-31","cited_by_count":18,"area":"ssm"},{"id":"2410.02113","title":"Mamba Neural Operator: Who Wins? Transformers vs. State-Space Models for PDEs","created":"2024-10-03","cited_by_count":16,"area":"ssm"},{"id":"2509.19633","title":"Mamba Modulation: On the Length Generalization of Mamba","created":"2025-09-23","cited_by_count":16,"area":"ssm"},{"id":"2405.16504","title":"Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation","created":"2024-05-26","cited_by_count":11,"area":"ssm"},{"id":"2412.14354","title":"State Space Models are Strong Text Rerankers","created":"2024-12-18","cited_by_count":10,"area":"ssm"},{"id":"2406.04320","title":"Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models","created":"2024-06-06","cited_by_count":8,"area":"ssm"},{"id":"2506.10918","title":"Sequential-Parallel Duality in Prefix Scannable Models","created":"2025-06-12","cited_by_count":8,"area":"ssm"},{"id":"2410.07145","title":"Stuffed Mamba: Oversized States Lead to the Inability to Forget","created":"2024-10-09","cited_by_count":7,"area":"ssm"},{"id":"2407.05489","title":"How Effective are State Space Models for Machine Translation?","created":"2024-07-07","cited_by_count":6,"area":"ssm"},{"id":"2503.10799","title":"Fixed-Point RNNs: Interpolating from Diagonal to Dense","created":"2025-03-13","cited_by_count":5,"area":"ssm"},{"id":"2406.02080","title":"LongSSM: On the Length Extension of State-space Models in Language Modelling","created":"2024-06-04","cited_by_count":3,"area":"ssm"},{"id":"2406.16518","title":"Vision Mamba-based autonomous crack segmentation on concrete, asphalt, and masonry surfaces","created":"2024-06-24","cited_by_count":3,"area":"ssm"},{"id":"2410.15678","title":"Revealing and Mitigating the Local Pattern Shortcuts of Mamba","created":"2024-10-21","cited_by_count":3,"area":"ssm"},{"id":"2411.00151","title":"NIMBA: Towards Robust and Principled Processing of Point Clouds With SSMs","created":"2024-10-31","cited_by_count":3,"area":"ssm"},{"id":"2509.17514","title":"Achilles' Heel of Mamba: Essential difficulties of the Mamba architecture demonstrated by synthetic data","created":"2025-09-22","cited_by_count":3,"area":"ssm"},{"id":"2510.04595","title":"SpikingMamba: Towards Energy-Efficient Large Language Models via Knowledge Distillation from Mamba","created":"2025-10-06","cited_by_count":3,"area":"ssm"},{"id":"2410.06846","title":"Joint Fine-tuning and Conversion of Pretrained Speech and Language Models towards Linear Complexity","created":"2024-10-09","cited_by_count":2,"area":"ssm"},{"id":"2505.11602","title":"Regularity and Stability Properties of Selective SSMs with Discontinuous Gating","created":"2025-05-16","cited_by_count":2,"area":"ssm"},{"id":"2506.11997","title":"pLSTM: parallelizable Linear Source Transition Mark networks","created":"2025-06-13","cited_by_count":2,"area":"ssm"},{"id":"2510.00399","title":"How Can Mamba Learn In Context with Outliers and Generalize Provably?","created":"2025-10-01","cited_by_count":2,"area":"ssm"},{"id":"2509.04226","title":"LISM: Long-range Integrative State space Models via Input-Latent State Interactions","created":"2025-09-04","cited_by_count":1,"area":"ssm"},{"id":"2510.12026","title":"Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning","created":"2025-10-14","cited_by_count":1,"area":"ssm"},{"id":"2602.17363","title":"2Mamba2Furious: Linear in Complexity, Competitive in Accuracy","created":"2026-02-19","cited_by_count":1,"area":"ssm"},{"id":"2603.05573","title":"Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View","created":"2026-03-05","cited_by_count":1,"area":"ssm"},{"id":"2603.12342","title":"MamTra: A Hybrid Mamba-Transformer Backbone for Speech Synthesis","created":"2026-03-12","cited_by_count":1,"area":"ssm"},{"id":"2604.07658","title":"Optimal Decay Spectra for Linear Recurrences","created":"2026-04-08","cited_by_count":1,"area":"ssm"},{"id":"2605.12770","title":"WriteSAE: Sparse Autoencoders for Recurrent State","created":"2026-05-12","cited_by_count":1,"area":"ssm"},{"id":"2607.03589","title":"Vision Non-Causal Trapezoidal Mamba: Eliminating Directional Scanning in Vision SSMs with Second-Order Dynamics","created":"2026-07-03","cited_by_count":1,"area":"ssm"},{"id":"2509.00935","title":"SCOUT: Toward Sub-Quadratic Attention via Segment Compression for Optimized Utility in Transformers","created":"2025-08-31","cited_by_count":0,"area":"ssm"},{"id":"2511.00315","title":"Language Modeling With Factorization Memory","created":"2025-10-31","cited_by_count":0,"area":"ssm"},{"id":"2605.09742","title":"TIDES: Implicit Time-Awareness in Selective State Space Models","created":"2026-05-10","cited_by_count":0,"area":"ssm"},{"id":"2605.10643","title":"A Single-Layer Model Can Do Language Modeling","created":"2026-05-11","cited_by_count":0,"area":"ssm"},{"id":"2606.17650","title":"MambaCount: Efficient Text-guided Open-vocabulary Object Counting with Spatial Sparse State Space Duality Block","created":"2026-06-16","cited_by_count":0,"area":"ssm"},{"id":"2609.33051","title":"SketchSSM: Write to the Full State, Read from a Compact Sketch","created":"2026-09-27","cited_by_count":0,"area":"ssm"}],"next_cursor":null}